libcll: an Extendable Python Toolkit for Complementary-Label Learning

TL;DR

libcll is an extensible Python toolkit that standardizes and simplifies complementary-label learning research by supporting various assumptions, datasets, and algorithms, thereby addressing inconsistency and accessibility issues.

Contribution

It introduces a unified platform for CLL research that supports multiple assumptions, datasets, and algorithms, streamlining experimentation and comparison.

Findings

Demonstrates utility through extensive ablation studies

Facilitates consistent evaluation across methods and datasets

Accelerates CLL research and development

Abstract

Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does not belong to -- are provided to the learning algorithm. Despite CLL's increasing popularity, previous studies highlight two main challenges: (1) inconsistent results arising from varied assumptions on complementary label generation, and (2) high barriers to entry due to the lack of a standardized evaluation platform across datasets and algorithms. To address these challenges, we introduce \texttt{libcll}, an extensible Python toolkit for CLL research. \texttt{libcll} provides a universal interface that supports a wide range of generation assumptions, both synthetic and real-world datasets, and key CLL algorithms. The toolkit is designed to mitigate inconsistencies and streamline the research process, with easy installation, comprehensive usage guides, and quickstart tutorials that facilitate efficient adoption and implementation of CLL techniques. Extensive ablation studies conducted with \texttt{libcll} demonstrate its utility in generating valuable insights to advance future CLL research.